/*
* Check a range of space and convert unwritten extents to written. Note that
* we are protected from truncate touching same part of extent tree by the
* fact that truncate code waits for all DIO to finish (thus exclusion from
* direct IO is achieved) and also waits for PageWriteback bits. Thus we
* cannot get to ext4_ext_truncate() before all IOs overlapping that range are
* completed (happens from ext4_free_ioend()).
*/
static int ext4_end_io(ext4_io_end_t *io)
{
struct inode *inode = io->inode;
loff_t offset = io->offset;
ssize_t size = io->size;
handle_t *handle = io->handle;
int ret = 0;
ext4_debug("ext4_end_io_nolock: io 0x%p from inode %lu,list->next 0x%p,"
"list->prev 0x%p\n",
io, inode->i_ino, io->list.next, io->list.prev);
io->handle = NULL; /* Following call will use up the handle */
ret = ext4_convert_unwritten_extents(handle, inode, offset, size);
if (ret < 0 && !ext4_forced_shutdown(EXT4_SB(inode->i_sb))) {
ext4_msg(inode->i_sb, KERN_EMERG,
"failed to convert unwritten extents to written "
"extents -- potential data loss! "
"(inode %lu, offset %llu, size %zd, error %d)",
inode->i_ino, offset, size, ret);
}
ext4_clear_io_unwritten_flag(io);
ext4_release_io_end(io);
return ret;
}
static int ext4_shutdown(struct super_block *sb, unsigned long arg)
{
struct ext4_sb_info *sbi = EXT4_SB(sb);
__u32 flags;
if (!capable(CAP_SYS_ADMIN))
return -EPERM;
if (get_user(flags, (__u32 __user *)arg))
return -EFAULT;
if (flags > EXT4_GOING_FLAGS_NOLOGFLUSH)
return -EINVAL;
if (ext4_forced_shutdown(sbi))
return 0;
ext4_msg(sb, KERN_ALERT, "shut down requested (%d)", flags);
switch (flags) {
case EXT4_GOING_FLAGS_DEFAULT:
freeze_bdev(sb->s_bdev);
set_bit(EXT4_FLAGS_SHUTDOWN, &sbi->s_ext4_flags);
thaw_bdev(sb->s_bdev, sb);
break;
case EXT4_GOING_FLAGS_LOGFLUSH:
set_bit(EXT4_FLAGS_SHUTDOWN, &sbi->s_ext4_flags);
if (sbi->s_journal && !is_journal_aborted(sbi->s_journal)) {
(void) ext4_force_commit(sb);
jbd2_journal_abort(sbi->s_journal, 0);
}
break;
case EXT4_GOING_FLAGS_NOLOGFLUSH:
set_bit(EXT4_FLAGS_SHUTDOWN, &sbi->s_ext4_flags);
if (sbi->s_journal && !is_journal_aborted(sbi->s_journal)) {
msleep(100);
jbd2_journal_abort(sbi->s_journal, 0);
}
break;
default:
return -EINVAL;
}
clear_opt(sb, DISCARD);
return 0;
}
/*
* write the buffer to the inline inode.
* If 'create' is set, we don't need to do the extra copy in the xattr
* value since it is already handled by ext4_xattr_ibody_inline_set.
* That saves us one memcpy.
*/
static void ext4_write_inline_data(struct inode *inode, struct ext4_iloc *iloc,
void *buffer, loff_t pos, unsigned int len)
{
struct ext4_xattr_entry *entry;
struct ext4_xattr_ibody_header *header;
struct ext4_inode *raw_inode;
int cp_len = 0;
if (unlikely(ext4_forced_shutdown(EXT4_SB(inode->i_sb))))
return;
BUG_ON(!EXT4_I(inode)->i_inline_off);
BUG_ON(pos + len > EXT4_I(inode)->i_inline_size);
raw_inode = ext4_raw_inode(iloc);
buffer += pos;
if (pos < EXT4_MIN_INLINE_DATA_SIZE) {
cp_len = pos + len > EXT4_MIN_INLINE_DATA_SIZE ?
EXT4_MIN_INLINE_DATA_SIZE - pos : len;
memcpy((void *)raw_inode->i_block + pos, buffer, cp_len);
len -= cp_len;
buffer += cp_len;
pos += cp_len;
}
if (!len)
return;
pos -= EXT4_MIN_INLINE_DATA_SIZE;
header = IHDR(inode, raw_inode);
entry = (struct ext4_xattr_entry *)((void *)raw_inode +
EXT4_I(inode)->i_inline_off);
memcpy((void *)IFIRST(header) + le16_to_cpu(entry->e_value_offs) + pos,
buffer, len);
}
int ext4_sync_file(struct file *file, loff_t start, loff_t end, int datasync)
{
struct inode *inode = file->f_mapping->host;
struct ext4_inode_info *ei = EXT4_I(inode);
journal_t *journal = EXT4_SB(inode->i_sb)->s_journal;
int ret = 0, err;
tid_t commit_tid;
bool needs_barrier = false;
if (unlikely(ext4_forced_shutdown(EXT4_SB(inode->i_sb))))
return -EIO;
J_ASSERT(ext4_journal_current_handle() == NULL);
trace_ext4_sync_file_enter(file, datasync);
if (inode->i_sb->s_flags & MS_RDONLY) {
/* Make sure that we read updated s_mount_flags value */
smp_rmb();
if (EXT4_SB(inode->i_sb)->s_mount_flags & EXT4_MF_FS_ABORTED)
ret = -EROFS;
goto out;
}
if (!journal) {
ret = __generic_file_fsync(file, start, end, datasync);
if (!ret)
ret = ext4_sync_parent(inode);
if (test_opt(inode->i_sb, BARRIER))
goto issue_flush;
goto out;
}
ret = file_write_and_wait_range(file, start, end);
if (ret)
return ret;
/*
* data=writeback,ordered:
* The caller's filemap_fdatawrite()/wait will sync the data.
* Metadata is in the journal, we wait for proper transaction to
* commit here.
*
* data=journal:
* filemap_fdatawrite won't do anything (the buffers are clean).
* ext4_force_commit will write the file data into the journal and
* will wait on that.
* filemap_fdatawait() will encounter a ton of newly-dirtied pages
* (they were dirtied by commit). But that's OK - the blocks are
* safe in-journal, which is all fsync() needs to ensure.
*/
if (ext4_should_journal_data(inode)) {
ret = ext4_force_commit(inode->i_sb);
goto out;
}
commit_tid = datasync ? ei->i_datasync_tid : ei->i_sync_tid;
if (journal->j_flags & JBD2_BARRIER &&
!jbd2_trans_will_send_data_barrier(journal, commit_tid))
needs_barrier = true;
ret = jbd2_complete_transaction(journal, commit_tid);
if (needs_barrier) {
issue_flush:
err = blkdev_issue_flush(inode->i_sb->s_bdev, GFP_KERNEL, NULL);
if (!ret)
ret = err;
}
out:
trace_ext4_sync_file_exit(inode, ret);
return ret;
}
